{"id":"https://openalex.org/W1754225409","doi":"https://doi.org/10.18653/v1/d15-1256","title":"Confounds and Consequences in Geotagged Twitter Data","display_name":"Confounds and Consequences in Geotagged Twitter Data","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1754225409","doi":"https://doi.org/10.18653/v1/d15-1256","mag":"1754225409"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1256","pdf_url":"https://www.aclweb.org/anthology/D15-1256.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1256.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065863233","display_name":"Umashanthi Pavalanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Umashanthi Pavalanathan","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065863233"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":8.4456,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96792818,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2138","last_page":"2148"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10557","display_name":"Social Media and Politics","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/geolocation","display_name":"Geolocation","score":0.9697438478469849},{"id":"https://openalex.org/keywords/demographics","display_name":"Demographics","score":0.6244218945503235},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.5480638742446899},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.529975175857544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5053315758705139},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.49250301718711853},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4730512201786041},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.469854474067688},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.4552816152572632},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4422608017921448},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43426376581192017},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.43165647983551025},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39048266410827637},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.3404434323310852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25055015087127686},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24594444036483765},{"id":"https://openalex.org/keywords/demography","display_name":"Demography","score":0.229261577129364},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17202302813529968},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1423993706703186},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12009704113006592}],"concepts":[{"id":"https://openalex.org/C22041718","wikidata":"https://www.wikidata.org/wiki/Q638949","display_name":"Geolocation","level":2,"score":0.9697438478469849},{"id":"https://openalex.org/C2780084366","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demographics","level":2,"score":0.6244218945503235},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.5480638742446899},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.529975175857544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5053315758705139},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.49250301718711853},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4730512201786041},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.469854474067688},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4552816152572632},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4422608017921448},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43426376581192017},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.43165647983551025},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39048266410827637},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.3404434323310852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25055015087127686},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24594444036483765},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.229261577129364},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17202302813529968},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1423993706703186},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12009704113006592},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.18653/v1/d15-1256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1256","pdf_url":"https://www.aclweb.org/anthology/D15-1256.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1506.02275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1506.02275","pdf_url":"https://arxiv.org/pdf/1506.02275","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:1754225409","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1506.02275","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.9094","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.9094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1256.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.878.886","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.878.886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.emnlp2015.org/proceedings/EMNLP/pdf/EMNLP256.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.882.7565","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.882.7565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/%7Ejeisenst/papers/pavalanathan-confounds-emnlp-2015.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1506.02275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1506.02275","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1256","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1256","pdf_url":"https://www.aclweb.org/anthology/D15-1256.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7260490651","display_name":"CAREER: Sociolinguistic Structure Induction","funder_award_id":"1452443","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1754225409.pdf","grobid_xml":"https://content.openalex.org/works/W1754225409.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W1498404717"],"related_works":["https://openalex.org/W2963929297","https://openalex.org/W2592751451","https://openalex.org/W2296291818","https://openalex.org/W3187921104","https://openalex.org/W2519502584","https://openalex.org/W3012605742","https://openalex.org/W2142889507","https://openalex.org/W3104019571","https://openalex.org/W2786963399","https://openalex.org/W3165152895","https://openalex.org/W2963699288","https://openalex.org/W2587320137","https://openalex.org/W2760355343","https://openalex.org/W31586431","https://openalex.org/W2953278188","https://openalex.org/W2406694909","https://openalex.org/W2911311763","https://openalex.org/W2292415828","https://openalex.org/W1985101747","https://openalex.org/W2291038164"],"abstract_inverted_index":{"Twitter":[0],"is":[1],"often":[2],"used":[3],"in":[4,32,79],"quantitative":[5],"studies":[6,16],"that":[7,48,112],"identify":[8],"geographically-preferred":[9],"topics,":[10],"writing":[11],"styles,":[12],"and":[13,44,59,63,70,84,94],"entities.":[14],"These":[15],"rely":[17],"on":[18,27,56],"either":[19],"GPS":[20],"coordinates":[21],"attached":[22],"to":[23,77,91,105],"individual":[24],"messages,":[25],"or":[26],"the":[28,46,113,123,129],"user-supplied":[29],"location":[30],"field":[31],"each":[33],"profile.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,51,96],"compare":[39],"these":[40,71,99],"data":[41],"acquisition":[42],"techniques":[43],"quantify":[45],"biases":[47],"they":[49],"introduce;":[50],"also":[52,110],"measure":[53],"their":[54],"effects":[55],"linguistic":[57,72],"analysis":[58],"textbased":[60],"geolocation.":[61],"GPS-tagging":[62],"selfreported":[64],"locations":[65],"yield":[66],"measurably":[67],"different":[68],"corpora,":[69],"differences":[73,78],"are":[74],"partially":[75],"attributable":[76],"dataset":[80],"composition":[81],"by":[82],"age":[83,93,130],"gender.":[85],"Using":[86],"a":[87],"latent":[88],"variable":[89],"model":[90],"induce":[92],"gender,":[95],"show":[97,111],"how":[98],"demographic":[100],"variables":[101],"interact":[102],"with":[103,119],"geography":[104],"affect":[106],"language":[107],"use.":[108],"We":[109],"accuracy":[114],"of":[115,131],"text-based":[116],"geolocation":[117],"varies":[118],"population":[120],"demographics,":[121],"giving":[122],"best":[124],"results":[125],"for":[126],"men":[127],"above":[128],"40.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}